Neil Kitchen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Neil Kitchen has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Patrick Grover
Victor Horsley Department of Neurosurgery, National Hospital for Neurology and Neurosurgery, London, UK
2 shared publications - Adrito Das
UCL Hawkes Institute, University College London, London, UK
1 shared publication - Alexander J. MacRobert
The "Head and Neck Optical Diagnostics Society" Council, Head & Neck Centre, University College Hospital, 250 Euston Road, London, NW1 2PG, UK
1 shared publication - Dahmane Oukrif
Department of Cellular Pathology, University College Hospital, London, 60 Whitfield Street, London W1T 4EU
1 shared publication - Danail Stoyanov
University College London
1 shared publication - Danyal Zaman Khan
Dept of Translational Neuroscience and Stroke, UCL Queen Square Institute of Neurology, University College London, London, UK
1 shared publication
Latest Publications
- Open Access
- 30 April 2025
- Published by Wolters Kluwer Health in Neurosurgery
- Vol. 98 (4) , 799-809
Automated Operative Phase and Step Recognition in Vestibular Schwannoma Surgery: Development and Preclinical Evaluation of a Deep Learning Neural Network (IDEAL Stage 0)
BACKGROUND AND OBJECTIVES: Machine learning (ML) in surgical video analysis offers promising prospects for training and decision support in surgery. The past decade has seen key advances in ML-based operative workflow analysis, though existing applications mostly feature shorter surgeries (5 hours duration), data-heavy surgeries, using VS resection as an exemplar. METHODS: A video dataset of 21 microscopic retrosigmoid VS resections was collected at a single institution over 3 years and underwent workflow annotation according to a previously agreed expert consensus (Approach, Excision, and Closure phases; and Debulking or Dissection steps within the Excision phase). Annotations were used to train a ML model consisting of a convolutional neural network and a recurrent neural network. 5-fold cross-validation was used, and performance metrics (accuracy, precision, recall, F1 score) were assessed for phase and step prediction. RESULTS: Median operative video time was 5 hours 18 minutes (IQR 3 hours 21 minutes-6 hours 1 minute). The “Tumor Excision” phase accounted for the majority of each case (median 4 hours 23 minutes), whereas “Approach and Exposure” (28 minutes) and “Closure” (17 minutes) comprised shorter phases. The ML model accurately predicted operative phases (accuracy 81%, weighted F1 0.83) and dichotomized steps (accuracy 86%, weighted F1 0.86). CONCLUSION: This study demonstrates that our ML model can accurately predict the surgical phases and intraphase steps in retrosigmoid VS resection. This demonstrates the successful application of ML in operative workflow recognition on low-volume, lengthy, data-heavy surgical videos. Despite this, there remains room for improvement in individual step classification. Future applications of ML in low-volume high-complexity operations should prioritize collaborative video sharing to overcome barriers to clinical translation.
- 30 April 2025
- Published by Wolters Kluwer Health in Neurosurgery
- Vol. 98 (4) , 799-809
Open AccessAutomated Operative Phase and Step Recognition in Vestibular Schwannoma Surgery: Development and Preclinical Evaluation of a Deep Learning Neural Network (IDEAL Stage 0)
BACKGROUND AND OBJECTIVES: Machine learning (ML) in surgical video analysis offers promising prospects for training and decision support in surgery. The past decade has seen key advances in ML-based operative workflow analysis, though existing applications mostly feature shorter surgeries (5 hours duration), data-heavy surgeries, using VS resection as an exemplar. METHODS: A video dataset of 21 microscopic retrosigmoid VS resections was collected at a single institution over 3 years and underwent workflow annotation according to a previously agreed expert consensus (Approach, Excision, and Closure phases; and Debulking or Dissection steps within the Excision phase). Annotations were used to train a ML model consisting of a convolutional neural network and a recurrent neural network. 5-fold cross-validation was used, and performance metrics (accuracy, precision, recall, F1 score) were assessed for phase and step prediction. RESULTS: Median operative video time was 5 hours 18 minutes (IQR 3 hours 21 minutes-6 hours 1 minute). The “Tumor Excision” phase accounted for the majority of each case (median 4 hours 23 minutes), whereas “Approach and Exposure” (28 minutes) and “Closure” (17 minutes) comprised shorter phases. The ML model accurately predicted operative phases (accuracy 81%, weighted F1 0.83) and dichotomized steps (accuracy 86%, weighted F1 0.86). CONCLUSION: This study demonstrates that our ML model can accurately predict the surgical phases and intraphase steps in retrosigmoid VS resection. This demonstrates the successful application of ML in operative workflow recognition on low-volume, lengthy, data-heavy surgical videos. Despite this, there remains room for improvement in individual step classification. Future applications of ML in low-volume high-complexity operations should prioritize collaborative video sharing to overcome barriers to clinical translation.
- Open Access
- 13 December 2023
- Published by Elsevier in Photodiagnosis and Photodynamic Therapy
- Vol. 45, 103923
Suppression of tumour growth from transplanted astrocytoma cells transfected with luciferase in mice by bioluminescence mediated, systemic, photodynamic therapy
- 13 December 2023
- Published by Elsevier in Photodiagnosis and Photodynamic Therapy
- Vol. 45, 103923
Open AccessSuppression of tumour growth from transplanted astrocytoma cells transfected with luciferase in mice by bioluminescence mediated, systemic, photodynamic therapy
- 29 August 2022
- Published by Taylor & Francis in British Journal Of Neurosurgery
- Vol. 36 (5) , 1
Brain fragments: daily notes and reminiscences
This small and short book of less than 200 pages is an absolute must for every neurosurgeon particularly those interested in our profession’s history and development during the 20th century. Writte...
- 29 August 2022
- Published by Taylor & Francis in British Journal Of Neurosurgery
- Vol. 36 (5) , 1
Brain fragments: daily notes and reminiscences
This small and short book of less than 200 pages is an absolute must for every neurosurgeon particularly those interested in our profession’s history and development during the 20th century. Writte...
- Top Cited PapersOpen Access
Survival Outcomes and Prognostic Factors in Glioblastoma
Background: IDH-wildtype glioblastoma is the most common malignant primary brain tumour in adults. As there is limited information on prognostic factors outside of clinical trials; thus, we conducted a retrospective study to characterise the glioblastoma population at our centre. Methods: Demographic, tumour molecular profiles, treatment, and survival data were collated for patients diagnosed with glioblastoma at our centre between July 2011 and December 2015. We used multivariate proportional hazard model associations with survival. Results: 490 patients were included; 60% had debulking surgery and 40% biopsy only. Subsequently, 56% had standard chemoradiotherapy, 25% had non-standard chemo/radio-therapy, and 19% had no further treatment. Overall survival was 9.2 months. In the multivariate analysis, longer survival was associated with debulking surgery vs. biopsy alone (14.9 vs. 8 months) (HR 0.54 [95% CI 0.41–0.70]), subsequent treatment after diagnosis (HR 0.12 [0.08–0.16]) (standard chemoradiotherapy [16.9 months] vs. non-standard regimens [9.2 months] vs. none [2.0 months]), tumour MGMT promotor methylation (HR 0.71 [0.58–0.87]), and younger age (hazard ratio vs. age < 50: 1.70 [1.26–2.30] for ages 50–59; 3.53 [2.65–4.70] for ages 60–69; 4.82 [3.54–6.56] for ages 70+). Conclusions: The median survival for patients with glioblastoma is less than a year. Younger age, debulking surgery, treatment with chemoradiotherapy, and MGMT promotor methylation are independently associated with longer survival.
Top Cited PapersOpen AccessSurvival Outcomes and Prognostic Factors in Glioblastoma
Background: IDH-wildtype glioblastoma is the most common malignant primary brain tumour in adults. As there is limited information on prognostic factors outside of clinical trials; thus, we conducted a retrospective study to characterise the glioblastoma population at our centre. Methods: Demographic, tumour molecular profiles, treatment, and survival data were collated for patients diagnosed with glioblastoma at our centre between July 2011 and December 2015. We used multivariate proportional hazard model associations with survival. Results: 490 patients were included; 60% had debulking surgery and 40% biopsy only. Subsequently, 56% had standard chemoradiotherapy, 25% had non-standard chemo/radio-therapy, and 19% had no further treatment. Overall survival was 9.2 months. In the multivariate analysis, longer survival was associated with debulking surgery vs. biopsy alone (14.9 vs. 8 months) (HR 0.54 [95% CI 0.41–0.70]), subsequent treatment after diagnosis (HR 0.12 [0.08–0.16]) (standard chemoradiotherapy [16.9 months] vs. non-standard regimens [9.2 months] vs. none [2.0 months]), tumour MGMT promotor methylation (HR 0.71 [0.58–0.87]), and younger age (hazard ratio vs. age < 50: 1.70 [1.26–2.30] for ages 50–59; 3.53 [2.65–4.70] for ages 60–69; 4.82 [3.54–6.56] for ages 70+). Conclusions: The median survival for patients with glioblastoma is less than a year. Younger age, debulking surgery, treatment with chemoradiotherapy, and MGMT promotor methylation are independently associated with longer survival.
- 30 June 2021
- Published by Springer Nature in Neurosurgical Review
- Vol. 45 (1) , 231-241
Surgery for cerebral cavernous malformations: a systematic review and meta-analysis
Background We sought to quantify the risks of neurosurgical excision of cerebral cavernous malformations (CCMs) in a systematic review of cohort studies. Methods We updated our previous systematic review by searching OVID Medline, OVID EMBASE, and the Cochrane Library from 1 January 2013 to 30 April 2019. The primary outcome was a composite of death attributed to CCM or surgery, non-fatal symptomatic intracerebral haemorrhage (ICH), or new or worsened persistent non-haemorrhagic focal neurological deficit (FND). Results We included 70 cohorts, 67 reporting surgery alone, and three compared surgery to conservative management. A total of 5,089 patients (median age 36 years, 52% female) underwent surgery (total follow-up 19,404 patient-years). The annual rate of the composite outcome was 4.2% (95% CI 2.9 to 5.7; 46 cohorts; I2 = 93%), which was higher in cohorts reporting exclusively brainstem CCM (6.0%, 95% CI 4.1–8.3; 25 cohorts, I2 = 92%) versus predominantly supratentorial CCM (2.4%, 95% CI 1.3–3.8, 21 cohorts, I2 = 86%, phet = 0.001). The annual rate of the composite outcome was higher in cohorts with > 95% presenting with ICH (6.1%, 95% CI 4.2–8.4; 23 cohorts, I2 = 93%) versus others (2.3%, 95% CI 1.2–3.7; 23 cohorts, I2 = 83%, phet = 0.001). The incidence of the composite outcome did not change over time in cohorts of exclusively brainstem CCM (p = 0.7) or predominantly supratentorial CCM (p = 0.5). Conclusions The risk of death, ICH, or FND after CCM excision is ~ 4%. This risk is higher for brainstem CCM and CCM that have caused ICH but has not changed over time. Trial registration This systematic review was registered (PROSPERO CRD42019131246).
- 30 June 2021
- Published by Springer Nature in Neurosurgical Review
- Vol. 45 (1) , 231-241
Surgery for cerebral cavernous malformations: a systematic review and meta-analysis
Background We sought to quantify the risks of neurosurgical excision of cerebral cavernous malformations (CCMs) in a systematic review of cohort studies. Methods We updated our previous systematic review by searching OVID Medline, OVID EMBASE, and the Cochrane Library from 1 January 2013 to 30 April 2019. The primary outcome was a composite of death attributed to CCM or surgery, non-fatal symptomatic intracerebral haemorrhage (ICH), or new or worsened persistent non-haemorrhagic focal neurological deficit (FND). Results We included 70 cohorts, 67 reporting surgery alone, and three compared surgery to conservative management. A total of 5,089 patients (median age 36 years, 52% female) underwent surgery (total follow-up 19,404 patient-years). The annual rate of the composite outcome was 4.2% (95% CI 2.9 to 5.7; 46 cohorts; I2 = 93%), which was higher in cohorts reporting exclusively brainstem CCM (6.0%, 95% CI 4.1–8.3; 25 cohorts, I2 = 92%) versus predominantly supratentorial CCM (2.4%, 95% CI 1.3–3.8, 21 cohorts, I2 = 86%, phet = 0.001). The annual rate of the composite outcome was higher in cohorts with > 95% presenting with ICH (6.1%, 95% CI 4.2–8.4; 23 cohorts, I2 = 93%) versus others (2.3%, 95% CI 1.2–3.7; 23 cohorts, I2 = 83%, phet = 0.001). The incidence of the composite outcome did not change over time in cohorts of exclusively brainstem CCM (p = 0.7) or predominantly supratentorial CCM (p = 0.5). Conclusions The risk of death, ICH, or FND after CCM excision is ~ 4%. This risk is higher for brainstem CCM and CCM that have caused ICH but has not changed over time. Trial registration This systematic review was registered (PROSPERO CRD42019131246).