AOAyooluwatomiwa I. Oloruntoba

Ayooluwatomiwa I. Oloruntoba

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ayooluwatomiwa I. Oloruntoba has a total of 67 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Fractional Ablative CO 2 Laser Parameters for Atrophic Acne Scar Treatment: An Ex Vivo Study

    by James Gaston, Andrew Maxwell, Eden Mane, Ayooluwatomiwa I. Oloruntoba, Ellis Tse‐Ann Choy, Eric Jung Yong Song, Michelle Rodrigues

    Background: Acne scarring affects up to 95% of individuals with acne vulgaris and carries a significant psychosocial burden. Fractional ablative CO 2 (FCO 2 ) laser is a treatment modality for acne scarring, though the histological effects of varying laser parameters remain incompletely characterized. Aims: To quantify ablation and collagen alteration across varying FCO 2 laser parameter settings on ex vivo human skin. Methods: Human skin samples were obtained from a consenting single donor ( n = 1) undergoing elective surgery. FCO 2 laser treatment was applied using varying power settings (5–30 W), dwell times (500–2000 μs), stacking (1–5 pulses), and pulse modes (standard‐pulse [SmartPulse], short‐pulse high‐peak [DEKAPulse], and high‐energy long‐dwell [HighPulse] modes) using SmartXide Punto by DEKA. Ablation width, depth, and collagen alteration were quantitatively assessed. Statistical analysis was performed using one‐way ANOVA. Pseudo‐replication was addressed by analysis performed on slide level means ( n = 3 independent slides per group). Results: Ablation width ranged from 105 to 375 μm, depth from 90 to 2612 μm, and collagen alteration from 23 to 174 μm laterally and 36–124 μm deep. HighPulse mode at 30 W with five stacks achieved the greatest ablation depth (2612 μm). DEKAPulse mode at 30 W and 1000 μs resulted in the largest collagen alteration zone (139 μm lateral, 101 μm deep). SmartPulse mode was the most superficially ablative. After correcting for pseudo‐replication, significant differences were identified across all parameter groups for all outcomes (all p ≤ 0.01), except lateral collagen alteration with DP stacking ( p = 0.149), deep collagen alteration with DP stacking ( p = 0.143), and deep collagen alteration with HP stacking ( p = 0.618). Conclusions: These exploratory single‐donor ex vivo findings raise the hypothesis that HighPulse mode may suit deep icepick and rolling scars, while DEKAPulse mode may be suitable for boxcar scars and SmartPulse mode for superficial atrophic scars. Multi‐donor and in vivo validation on facial scarred skin is needed to validate these findings.

  • Open Access

    Cardiac involvement in severe cutaneous adverse reactions: a retrospective observational cohort study of drug reaction with eosinophilia and systemic symptoms and Stevens–Johnson syndrome/toxic epidermal necrolysis at a major Australian tertiary hospital

    by Sang Jin Han, Ayooluwatomiwa I Oloruntoba, Angela Meng, Thea Bosco, Eldho Paul, Linda Graudins, Michelle S Goh, Johannes S Kern, Celia Zubrinich, Ar Kar Aung

    Background: Drug reaction with eosinophilia and systemic symptoms (DRESS), Stevens–Johnson syndrome (SJS) and toxic epidermal necrolysis (TEN) are life-threatening adverse medication reactions, often with multiorgan involvement. Cardiac involvement in these conditions has not been well characterized. Objectives: To evaluate the prevalence, clinical spectrum and outcomes of cardiac involvement in patients diagnosed with DRESS and SJS/TEN. Methods: A single-centre retrospective cohort study was conducted. Patients with DRESS or SJS/TEN seen between January 2014 and January 2024 were identified through the hospital adverse drug reaction database. Cardiac involvement was defined as the presence of cardiac symptoms accompanied by any new abnormality detected on electrocardiograms, cardiac biomarkers and/or cardiac imaging during admission. Results: In total, 158 patients were included: 79 with DRESS and 79 with SJS/TEN. Cardiac involvement was identified in 15% of cases of DRESS and 6% of cases of SJS/TEN. Cardiovascular risk factors were prevalent across both conditions, with hypertension being the most common. Cardiac symptoms were reported in up to 20% of cases, with dyspnoea being the most frequent. Of those who had cardiac investigations, new electrocardiographic abnormalities were detected in up to 42% of patients. Intensive care unit (ICU) admissions and mortality were higher with SJS/TEN, but there was no mortality attributable to cardiac involvement. Antibiotics were the most frequently implicated medications in both groups. In the DRESS subgroup analysis, cardiac involvement was associated with higher rates of renal involvement (100% vs. 64%, P = 0.01) and ICU admission [67% vs. 34%, odds ratio (OR) 3.83, 95% confidence interval (CI) 1.04–14.1; P = 0.04], but was less common with antibiotic exposure as a cause of DRESS (58% vs. 84%, OR 0.28, 95% CI 0.07–1.03; P = 0.06). Conclusions: Cardiac involvement is an under-recognized but clinically important feature of DRESS and SJS/TEN. Our findings highlight the contribution of cardiac dysfunction to morbidity and support routine cardiac assessment in patients with severe cutaneous adverse reactions. Larger prospective studies and national drug reaction registries are needed to better define the burden and guide care.

  • Open Access

    Safety and Tolerability of Fractional CO 2 Lasers for Facial Rejuvenation Across Fitzpatrick Skin Phototypes I– IV : Retrospective Cohort Study

    by Ayooluwatomiwa I. Oloruntoba, Michelle Rodrigues

    Background: Fractional CO 2 laser is an effective treatment for skin rejuvenation, although pigmentary complications remain a clinical consideration. Newer generation fractional CO 2 laser systems include pulse modes such as HighPulse (HP), which deliver high energy over a shortened dwell time, reducing the duration of energy delivery per microbeam with the aim of limiting thermal diffusion beyond the ablation zone. Methods: We conducted a single‐center retrospective study of 38 patients (Fitzpatrick skin phototypes I–IV) treated with fractional CO 2 laser using HP mode for facial rejuvenation. Pain scores and adverse events were recorded, stratified by skin type and anesthetic use. Results: Mean pain score was 4.8, with no statistically significant difference between patients who received topical anesthetic (LMX4) and those who did not. Pain scores did not differ significantly across skin phototypes I–IV. Erythema occurred in 50% of patients and edema in 24%, all of which were transient. No cases of blistering, post‐inflammatory hyperpigmentation, or scarring were documented in routine clinical records, although the true incidence may be underestimated. Erythema rates did not differ significantly by anesthetic use. Conclusions: In this preliminary cohort, the HP fractional laser was associated with transient short‐term adverse effects and no documented pigmentary complications among patients with Fitzpatrick skin types I–IV. These findings are descriptive and are not generalizable to Fitzpatrick phototypes V–VI, which were not represented.


  • Open Access

    Lichen Planus Follicularis Tumidus

    by A. I. Oloruntoba, Saurabh Prakash, Ryan Toholka


  • Assessment of image quality on the diagnostic performance of clinicians and deep learning models: Cross‐sectional comparative reader study

    by A. I. Oloruntoba, M. Asghari‐Jafarabadi, M. Sashindranath, Å. Ingvar, N. R. Adler, C. Vico‐Alonso, L. Niklasson, A. L. Caixinha, E. Hiscutt, Z. Holmes, et al.

    Background: Skin cancer is a prevalent and clinically significant condition, with early and accurate diagnosis being crucial for improved patient outcomes. Dermoscopy and artificial intelligence (AI) hold promise in enhancing diagnostic accuracy. However, the impact of image quality, particularly high dynamic range (HDR) conversion in smartphone images, on diagnostic performance remains poorly understood.Objective: This study aimed to investigate the effect of varying image qualities, including HDR‐enhanced dermoscopic images, on the diagnostic capabilities of clinicians and a convolutional neural network (CNN) model.Methods: Eighteen dermatology clinicians assessed 303 images of 101 skin lesions that were categorized into three image quality groups: low quality (LQ), high quality (HQ) and enhanced quality (EQ) produced using HDR‐style conversion. Clinicians participated in a two part reader study that required their diagnosis, management and confidence level for each image assessed.Results: In the binary classification of lesions, clinicians had the greatest diagnostic performance with HQ images, with sensitivity (77.3%; CI 69.1–85.5), specificity (63.1%; CI 53.7–72.5) and accuracy (70.2%; CI 61.3–79.1). For the multiclass classification, the overall performance was also best with HQ images, attaining the greatest specificity (91.9%; CI 83.2–95.0) and accuracy (51.5%; CI 48.4–54.7). Clinicians had a superior performance (median correct diagnoses) to the CNN model for the binary classification of LQ and EQ images, but their performance was comparable on the HQ images. However, in the multiclass classification, the CNN model significantly outperformed the clinicians on HQ images (p < 0.01).Conclusion: This study highlights the importance of image quality on the diagnostic performance of clinicians and deep learning models. This has significant implications for telehealth reporting and triage.


  • Consensus versus discordance in the classification of borderline melanocytic lesions between dermatopathologists and artificial intelligence: An Australian cohort study

    by Nicholas M. Muller, Chantal Rutjes, Samuel X. Tan, Nisal Vipulaguna, Ayooluwatomiwa Oloruntoba, Toan Nguyen, Lena von Schuckmann, Brigid Betz‐Stablein, Kiarash Khosrotehrani, Zongyuan Ge, et al.

  • Open Access

    Examining labelling guidelines for AI‐based software as a medical device: A review and analysis of dermatology mobile applications in Australia

    by Ayooluwatomiwa Oloruntoba, Åsa Ingvar, Maithili Sashindranath, Ojochonu Anthony, Lisa Abbott, Pascale Guitera, Tony Caccetta, Monika Janda, H. Peter Soyer, Victoria Mar

    In recent years, there has been a surge in the development of AI‐based Software as a Medical Device (SaMD), particularly in visual specialties such as dermatology. In Australia, the Therapeutic Goods Administration (TGA) regulates AI‐based SaMD to ensure its safe use. Proper labelling of these devices is crucial to ensure that healthcare professionals and the general public understand how to use them and interpret results accurately. However, guidelines for labelling AI‐based SaMD in dermatology are lacking, which may result in products failing to provide essential information about algorithm development and performance metrics. This review examines existing labelling guidelines for AI‐based SaMD across visual medical specialties, with a specific focus on dermatology. Common recommendations for labelling are identified and applied to currently available dermatology AI‐based SaMD mobile applications to determine usage of these labels. Of the 21 AI‐based SaMD mobile applications identified, none fully comply with common labelling recommendations. Results highlight the need for standardized labelling guidelines. Ensuring transparency and accessibility of information is essential for the safe integration of AI into health care and preventing potential risks associated with inaccurate clinical decisions.


  • Bridging the gap in skin cancer research for Australians with skin of colour

    by Ayooluwatomiwa I Oloruntoba, Michelle Rodrigues


  • Open Access

    Assessing the Generalizability of Deep Learning Models Trained on Standardized and Nonstandardized Images and Their Performance Against Teledermatologists: Retrospective Comparative Study

    by Ayooluwatomiwa I Oloruntoba, Tine Vestergaard, Toan D Nguyen, Zhen Yu, Maithili Sashindranath, Brigid Betz-Stablein, H Peter Soyer, Zongyuan Ge, Victoria Mar

    Background: Convolutional neural networks (CNNs) are a type of artificial intelligence that shows promise as a diagnostic aid for skin cancer. However, the majority are trained using retrospective image data sets with varying image capture standardization. Objective: The aim of our study was to use CNN models with the same architecture—trained on image sets acquired with either the same image capture device and technique (standardized) or with varied devices and capture techniques (nonstandardized)—and test variability in performance when classifying skin cancer images in different populations. Methods: In all, 3 CNNs with the same architecture were trained. CNN nonstandardized (CNN-NS) was trained on 25,331 images taken from the International Skin Imaging Collaboration (ISIC) using different image capture devices. CNN standardized (CNN-S) was trained on 177,475 MoleMap images taken with the same capture device, and CNN standardized number 2 (CNN-S2) was trained on a subset of 25,331 standardized MoleMap images (matched for number and classes of training images to CNN-NS). These 3 models were then tested on 3 external test sets: 569 Danish images, the publicly available ISIC 2020 data set consisting of 33,126 images, and The University of Queensland (UQ) data set of 422 images. Primary outcome measures were sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC). Teledermatology assessments available for the Danish data set were used to determine model performance compared to teledermatologists. Results: When tested on the 569 Danish images, CNN-S achieved an AUROC of 0.861 (95% CI 0.830-0.889) and CNN-S2 achieved an AUROC of 0.831 (95% CI 0.798-0.861; standardized models), with both outperforming CNN-NS (nonstandardized model; P=.001 and P=.009, respectively), which achieved an AUROC of 0.759 (95% CI 0.722-0.794). When tested on 2 additional data sets (ISIC 2020 and UQ), CNN-S (P<.001 and P<.001, respectively) and CNN-S2 (P=.08 and P=.35, respectively) still outperformed CNN-NS. When the CNNs were matched to the mean sensitivity and specificity of the teledermatologists on the Danish data set, the models’ resultant sensitivities and specificities were surpassed by the teledermatologists. However, when compared to CNN-S, the differences were not statistically significant (sensitivity: P=.10; specificity: P=.053). Performance across all CNN models as well as teledermatologists was influenced by image quality. Conclusions: CNNs trained on standardized images had improved performance and, therefore, greater generalizability in skin cancer classification when applied to unseen data sets. This finding is an important consideration for future algorithm development, regulation, and approval.


  • Open Access

    Assessing Generalizability of Deep Learning Models Trained on Standardized and Nonstandardized Images and Their Performance Against Teledermatologists

    by Ibukun Oloruntoba, Toan D Nguyen, Zongyuan Ge, Tine Vestergaard, Victoria Mar

    Background: Convolutional neural networks (CNNs) are a type of artificial intelligence that show promise as a diagnostic aid for skin cancer. However, the majority are trained using retrospective image data sets of varying quality and image capture standardization. Objective: The aim of our study is to use CNN models with the same architecture, but different training image sets, and test variability in performance when classifying skin cancer images in different populations, acquired with different devices. Additionally, we wanted to assess the performance of the models against Danish teledermatologists when tested on images acquired from Denmark. Methods: Three CNNs with the same architecture were trained. CNN-NS was trained on 25,331 nonstandardized images taken from the International Skin Imaging Collaboration using different image capture devices. CNN-S was trained on 235,268 standardized images, and CNN-S2 was trained on 25,331 standardized images (matched for number and classes of training images to CNN-NS). Both standardized data sets (CNN-S and CNN-S2) were provided by Molemap using the same image capture device. A total of 495 Danish patients with 569 images of skin lesions predominantly involving Fitzpatrick skin types II and III were used to test the performance of the models. Four teledermatologists independently diagnosed and assessed the images taken of the lesions. Primary outcome measures were sensitivity, specificity, and area under the curve of the receiver operating characteristic (AUROC). Results: A total of 569 images were taken from 495 patients (n=280, 57% women, n=215, 43% men; mean age 55, SD 17 years) for this study. On these images, CNN-S achieved an AUROC of 0.861 (95% CI 0.830-0.889; P<.001), and CNN-S2 achieved an AUROC of 0.831 (95% CI 0.798-0.861; P=.009), with both outperforming CNN-NS, which achieved an AUROC of 0.759 (95% CI 0.722-0.794; P<.001; P=.009). When the CNNs were matched to the mean sensitivity and specificity of the teledermatologists, the model’s resultant sensitivities and specificities were surpassed by the teledermatologists. However, when compared to CNN-S, the differences were not statistically significant (P=.10; P=.05). Performance across all CNN models and teledermatologists was influenced by the image quality. Conclusions: CNNs trained on standardized images had improved performance and therefore greater generalizability in skin cancer classification when applied to an unseen data set. This is an important consideration for future algorithm development, regulation, and approval. Further, when tested on these unseen test images, the teledermatologists clinically outperformed all the CNN models; however, the difference was deemed to be statistically insignificant when compared to CNN-S. Conflicts of Interest: VM received speakers fees from Merck, Eli Lily, Novartis and Bristol Myers Squibb. VM is the principal investigator for a clinical trial funded by the Victorian Department of Health and Human Services with 1:1 contribution from MoleMap.