Assemblée Générale du GdR, 6-8 octobre 2025
La prochaine Assemblée Générale du GdR se déroulera à La Grande-Motte Presqu’Ile du Ponant, du...
13 December 2023
Catégorie : Stagiaire
Internship at IMT Atlantique - LaTIM UMR 1101, Inserm in Brest
M2 - Last year engineering student
Deep characterization of prostate cancer in multi-parametric imaging
IMT Atlantique - LaTIM UMR 1101, Inserm is looking for a M2 student motivated by image analysis with a particular interest in deep learning applications.
Title: Deep characterization of prostate cancer in multi-parametric imaging
Context: With over one million new diagnoses and 350,000 deaths worldwide each year, Prostate Cancer (PCa) is the second most common cancer in men. Recommended before biopsies, multi-parametric Magnetic Resonance Imaging (mp-MRI), which consists in acquiring multiple dedicated diffusion and anatomical MRI sequences, is playing an increasing role in early diagnosis. However, visual analysis of prostatic mp-MRI data requires considerable expertise due to the heterogeneity of pathological patterns, and suffers from poor inter-reader agreement, sub-optimal interpretation and over-diagnosis. Furthermore, it does not allow to determine the cancer aggressiveness, as characterized by the Gleason Score (GS). In a context where active surveillance is recommended when a low-aggressivity cancer has been identified, it is crucial to accurately characterize cancer progression using non-invasive methods. For all these reasons, research into Deep Learning (DL) based diagnosis models to help radiologists analyze mp-MRI has been prolific in recent years. To improve the performance of these models and move towards the clinical transfer of such tools, we propose to focus on multi-modal information fusion for detecting/segmenting prostate lesions and characterizing their aggressiveness, major challenges as differentiation between low- and medium/high-grade PCa is an important clinical determinant.
Internship topic: In this context, we are interested in the development of multi-task networks that can simultaneously detect/segment lesions and characterize their clinical stage. The main methodological objective of the internship will be to take advantage of redundancies and complementarities between channels by considering four mp-MRI sequences (T2, ADC, B2000, perfusion), thereby extending bimodal fusion approaches previously proposed for PCa imaging that used only T2 and ADC. A priority will be given to the development of innovative DL architectures that can leverage the various modalities through cross-modality learning. Cross-modality learning is usually performed with architectures containing many layers specific to each modality, which does not allow to fully exploit potentially valuable inter-modal information. Efforts will be devoted to the design of more compact models by widely re-using network parameters (e.g., sharing convolution kernels between modalities). Through cross-modality learning, the contributions will aim at obtaining more accurate and synthetic models, with associated uncertainty quantification. Multi-modal medical Transformers models for segmentation and detection will be primarily considered, in line with prior research conducted at LaTIM.
Candidate profile: We are looking for a M2 student motivated by image analysis with a particular interest in DL applications. A background in biomedical or medical imaging and an experience with Python programming language and Pytorch package are a plus. Good communication and team working skills are also required as the intern will work in close collaboration with another team from INSA Lyon / CREATIS laboratory located in Lyon, France. A good ability to communicate in English as well as a fluent English for reading and writing scientific articles are also required.
Internship information: