Precision medicine holds the potential to revolutionize healthcare by providing every patient with personalized treatments and decisions tailored to his or her individual needs. This might be enabled by the large influx of potentially diagnostic information from new sources such as genetics and modern imaging techniques, provided the relevant information can be extracted. One such framework that has started to demonstrate promise in radiology, especially in the assessment of cancer, is radiomics; the practice of characterizing images by extracting a substantial amount of quantitative mathematical descriptors. This success has largely been enabled by artificial intelligence (AI) and machine learning developments that are capable of handling the big data arrays. Using radiomics, researchers have been able to build prediction models capable of assisting and informing doctors in important decisions such as risk assessment or the choice of treatment. But even though radiomics has shown promise in preliminary studies, there is still a long way to go before radiomics and related AI applications can become routine tools in clinics. The road from patient admission to release is long, and all its intricate steps need to be studied in detail to establish the AI models' benefits and safety. Deep learning is an incredibly powerful AI technique that has revolutionized many areas of science and industry such as recommender systems and protein folding. The technique has demonstrated particular capabilities in image analysis, such as the ability to drive cars autonomously and generate realistic-looking images from scratch. However, the recent advances in deep learning have largely been segregated from the radiomics domain, even though they can synergize with radiomics by performing complementary tasks such as image segmentation and denoising. There is considerable potential for DL and radiomics to cooperatively reinforce each other that so far has been majorly unexplored. This thesis investigates the application of radiomics and deep learning in the context of prostate cancer. It focuses on the clinical perspective of where machine learning implementations are most likely to have a beneficial real-world impact. A key contribution is the deployment aspect: the models are not simply proofs of concept but are conceived and applied in a practical scenario, from patient admission to treatment decision. The specific areas studied include automatic organ segmentation in medical images, automatic quality assurance of segmentations, image processing, and radiomic feature analysis. Finally, a comprehensive study is performed on predicting essential pathological variables with AI, which so far has not been studied previously. Taken together, the methods outlined in this thesis constitute a concrete pathway of how AI can be used to bolster the steps along the patient's clinical trajectory. Successful applications of these methods hold the potential to reduce the workload of clinicians and improve patient outcomes.

HYBRID DEEP LEARNING AND RADIOMICS MODELS FOR ASSESSMENT OF CLINICALLY RELEVANT PROSTATE CANCER / L.j. Isaksson ; internal advisor: S. Gandini ; external advisor: A. Bhalerao ; phd coordinator: S. Minucci. - : . Dipartimento di Oncologia ed Emato-Oncologia, 2022. ((34. ciclo, Anno Accademico 2022.

HYBRID DEEP LEARNING AND RADIOMICS MODELS FOR ASSESSMENT OF CLINICALLY RELEVANT PROSTATE CANCER

L.J. Isaksson
2022

Abstract

Precision medicine holds the potential to revolutionize healthcare by providing every patient with personalized treatments and decisions tailored to his or her individual needs. This might be enabled by the large influx of potentially diagnostic information from new sources such as genetics and modern imaging techniques, provided the relevant information can be extracted. One such framework that has started to demonstrate promise in radiology, especially in the assessment of cancer, is radiomics; the practice of characterizing images by extracting a substantial amount of quantitative mathematical descriptors. This success has largely been enabled by artificial intelligence (AI) and machine learning developments that are capable of handling the big data arrays. Using radiomics, researchers have been able to build prediction models capable of assisting and informing doctors in important decisions such as risk assessment or the choice of treatment. But even though radiomics has shown promise in preliminary studies, there is still a long way to go before radiomics and related AI applications can become routine tools in clinics. The road from patient admission to release is long, and all its intricate steps need to be studied in detail to establish the AI models' benefits and safety. Deep learning is an incredibly powerful AI technique that has revolutionized many areas of science and industry such as recommender systems and protein folding. The technique has demonstrated particular capabilities in image analysis, such as the ability to drive cars autonomously and generate realistic-looking images from scratch. However, the recent advances in deep learning have largely been segregated from the radiomics domain, even though they can synergize with radiomics by performing complementary tasks such as image segmentation and denoising. There is considerable potential for DL and radiomics to cooperatively reinforce each other that so far has been majorly unexplored. This thesis investigates the application of radiomics and deep learning in the context of prostate cancer. It focuses on the clinical perspective of where machine learning implementations are most likely to have a beneficial real-world impact. A key contribution is the deployment aspect: the models are not simply proofs of concept but are conceived and applied in a practical scenario, from patient admission to treatment decision. The specific areas studied include automatic organ segmentation in medical images, automatic quality assurance of segmentations, image processing, and radiomic feature analysis. Finally, a comprehensive study is performed on predicting essential pathological variables with AI, which so far has not been studied previously. Taken together, the methods outlined in this thesis constitute a concrete pathway of how AI can be used to bolster the steps along the patient's clinical trajectory. Successful applications of these methods hold the potential to reduce the workload of clinicians and improve patient outcomes.
JERECZEK, BARBARA ALICJA
MINUCCI, SAVERIO
deep learning; radiomics; cancer; medical image; machine learning; prediction; mri; ai; artificial intelligence
Settore MED/36 - Diagnostica per Immagini e Radioterapia
HYBRID DEEP LEARNING AND RADIOMICS MODELS FOR ASSESSMENT OF CLINICALLY RELEVANT PROSTATE CANCER / L.j. Isaksson ; internal advisor: S. Gandini ; external advisor: A. Bhalerao ; phd coordinator: S. Minucci. - : . Dipartimento di Oncologia ed Emato-Oncologia, 2022. ((34. ciclo, Anno Accademico 2022.
Doctoral Thesis
File in questo prodotto:
File Dimensione Formato  
phd_unimi_R12392.pdf

accesso aperto

Descrizione: Dissertation
Tipologia: Post-print, accepted manuscript ecc. (versione accettata dall'editore)
Dimensione 9.66 MB
Formato Adobe PDF
9.66 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/946529
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact