Lucia Zanchi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Lucia Zanchi has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Christian Salvatore
Ailice Labs, Department of Science, Technology and Society, University School for Advanced Studies IUSS Pavia, 27100 Pavia, Italy
2 shared publications - Francesco Raspagliesi
Gynecological Oncology Unit, Fondazione IRCCS—Istituto Nazionale Tumori, 20133 Milano, Italy
2 shared publications - Giorgio Bogani
Gynaecological Oncology Unit, Fondazione IRCCS Istituto Nazionale dei Tumori di Milano, 20133 Milano, Italy
2 shared publications - Giuseppina Calareso
Department of Radiology and Diagnostics, Fondazione IRCCS Istituto Nazionale dei Tumori, Milan, Italy
2 shared publications - Isabella Castiglioni
Department of Physics ‘‘Giuseppe Occhialini”, University of Milan-Bicocca, 20126 Milan, Italy
2 shared publications - Matteo Interlenghi
DeepTrace Technologies S.R.L., Via Conservatorio 17, 20122 Milan, Italy
2 shared publications
Latest Publications
- Open Access
- 11 March 2026
- Published by MDPI AG in Preprints.org
Developing a Radiomics and Machine Learning Model Applied to Magnetic Resonance Images for Differential Diagnosis of Myometrial Tumors
Background. The preoperative differential diagnosis of myometrial lesions remains a significant challenge when using conventional imaging techniques, such as ultrasound (US) and magnetic resonance imaging (MRI). Radiomics and machine learning, which leverage quantitative features beyond human visual perception, are increasingly recognized as promising tools for improving differential diagnosis in gynecology. Methods. This retrospective study included patients who underwent surgery for uterine masses and had preoperative MR. A machine learning model was developed to analyze radiomic features extracted from T2-weighted and diffusion-weighted MR images. Results. 44 subjects were included: 19 (43.2%) classified as "sarcoma" and 25 (56.8%) as "fibroid" based on histology after surgery. This dataset was used for training and cross-validation of different models. Three models, comprising ensembles of machine learning classifiers (random forests, support vector machines, and k-nearest neighbors), were developed for binary classification using histological diagnosis as reference standard. The best-performing model achieved the following results: AUC 90%, accuracy 82%, sensitivity 95%, specificity 72%, PPV 72%, and NPV 95%. Conclusions. Our model demonstrated high sensitivity and moderate accuracy, suggesting its potential as a valuable tool for assisting clinicians in the preliminary assessment of myometrial lesions and guiding decision-making toward conservative management in cases of non-suspicious masses.
- 11 March 2026
- Published by MDPI AG in Preprints.org
Open AccessDeveloping a Radiomics and Machine Learning Model Applied to Magnetic Resonance Images for Differential Diagnosis of Myometrial Tumors
Background. The preoperative differential diagnosis of myometrial lesions remains a significant challenge when using conventional imaging techniques, such as ultrasound (US) and magnetic resonance imaging (MRI). Radiomics and machine learning, which leverage quantitative features beyond human visual perception, are increasingly recognized as promising tools for improving differential diagnosis in gynecology. Methods. This retrospective study included patients who underwent surgery for uterine masses and had preoperative MR. A machine learning model was developed to analyze radiomic features extracted from T2-weighted and diffusion-weighted MR images. Results. 44 subjects were included: 19 (43.2%) classified as "sarcoma" and 25 (56.8%) as "fibroid" based on histology after surgery. This dataset was used for training and cross-validation of different models. Three models, comprising ensembles of machine learning classifiers (random forests, support vector machines, and k-nearest neighbors), were developed for binary classification using histological diagnosis as reference standard. The best-performing model achieved the following results: AUC 90%, accuracy 82%, sensitivity 95%, specificity 72%, PPV 72%, and NPV 95%. Conclusions. Our model demonstrated high sensitivity and moderate accuracy, suggesting its potential as a valuable tool for assisting clinicians in the preliminary assessment of myometrial lesions and guiding decision-making toward conservative management in cases of non-suspicious masses.
- Open Access
- 6 October 2023
- Published by MDPI AG in Diagnostics
- Vol. 13 (19) , 3139
Using Radiomics and Machine Learning Applied to MRI to Predict Response to Neoadjuvant Chemotherapy in Locally Advanced Cervical Cancer
Neoadjuvant chemotherapy plus radical surgery could be a safe alternative to chemo-radiation in cervical cancer patients who are not willing to receive radiotherapy. The response to neoadjuvant chemotherapy is the main factor influencing the need for adjunctive treatments and survival. In the present paper we aim to develop a machine learning model based on cervix magnetic resonance imaging (MRI) images to stratify the single-subject risk of cervical cancer. We collected MRI images from 72 subjects. Among these subjects, 28 patients (38.9%) belonged to the “Not completely responding” class and 44 patients (61.1%) belonged to the ’Completely responding‘ class according to their response to treatment. This image set was used for the training and cross-validation of different machine learning models. A robust radiomic approach was applied, under the hypothesis that the radiomic features could be able to capture the disease heterogeneity among the two groups. Three models consisting of three ensembles of machine learning classifiers (random forests, support vector machines, and k-nearest neighbor classifiers) were developed for the binary classification task of interest (“Not completely responding” vs. “Completely responding”), based on supervised learning, using response to treatment as the reference standard. The best model showed an ROC-AUC (%) of 83 (majority vote), 82.3 (mean) [79.9–84.6], an accuracy (%) of 74, 74.1 [72.1–76.1], a sensitivity (%) of 71, 73.8 [68.7–78.9], and a specificity (%) of 75, 74.2 [71–77.5]. In conclusion, our preliminary data support the adoption of a radiomic-based approach to predict the response to neoadjuvant chemotherapy.
- 6 October 2023
- Published by MDPI AG in Diagnostics
- Vol. 13 (19) , 3139
Open AccessUsing Radiomics and Machine Learning Applied to MRI to Predict Response to Neoadjuvant Chemotherapy in Locally Advanced Cervical Cancer
Neoadjuvant chemotherapy plus radical surgery could be a safe alternative to chemo-radiation in cervical cancer patients who are not willing to receive radiotherapy. The response to neoadjuvant chemotherapy is the main factor influencing the need for adjunctive treatments and survival. In the present paper we aim to develop a machine learning model based on cervix magnetic resonance imaging (MRI) images to stratify the single-subject risk of cervical cancer. We collected MRI images from 72 subjects. Among these subjects, 28 patients (38.9%) belonged to the “Not completely responding” class and 44 patients (61.1%) belonged to the ’Completely responding‘ class according to their response to treatment. This image set was used for the training and cross-validation of different machine learning models. A robust radiomic approach was applied, under the hypothesis that the radiomic features could be able to capture the disease heterogeneity among the two groups. Three models consisting of three ensembles of machine learning classifiers (random forests, support vector machines, and k-nearest neighbor classifiers) were developed for the binary classification task of interest (“Not completely responding” vs. “Completely responding”), based on supervised learning, using response to treatment as the reference standard. The best model showed an ROC-AUC (%) of 83 (majority vote), 82.3 (mean) [79.9–84.6], an accuracy (%) of 74, 74.1 [72.1–76.1], a sensitivity (%) of 71, 73.8 [68.7–78.9], and a specificity (%) of 75, 74.2 [71–77.5]. In conclusion, our preliminary data support the adoption of a radiomic-based approach to predict the response to neoadjuvant chemotherapy.