Clinical applications of textural analysis in non-small cell lung cancer

Abstract

Lung cancer is the leading cause of cancer mortality worldwide. Treatment pathways include regular cross-sectional imaging, generating large data sets which present intriguing possibilities for exploitation beyond standard visual interpretation. This additional data mining has been termed "radiomics" and includes semantic and agnostic approaches. Textural analysis (TA) is an example of the latter, and uses a range of mathematically derived features to describe an image or region of an image. Often TA is used to describe a suspected or known tumour. TA is an attractive tool as large existing image sets can be submitted to diverse techniques for data processing, presentation, interpretation and hypothesis testing with annotated clinical outcomes. There is a growing anthology of published data using different TA techniques to differentiate between benign and malignant lung nodules, differentiate tissue subtypes of lung cancer, prognosticate and predict outcome and treatment response, as well as predict treatment side effects and potentially aid radiotherapy planning. The aim of this systematic review is to summarize the current published data and understand the potential future role of TA in managing lung cancer.

Tumor heterogeneity of pancreas head cancer assessed by CT texture analysis: association with survival outcomes after curative resection

“…The biologic importance of intratumoral heterogeneity in malignant tumors has received attention in recent studies, and there is accumulating evidence that intratumoral heterogeneity at the cellular, molecular, and morphological levels has an important effect on tumor recurrence, therapeutic response, and survival in patients with malignant tumors, including pancreatic cancer 10 – 12 . From the imaging perspective, intratumoral heterogeneity can be quantified non-invasively by computed tomography (CT) texture analysis, which has a potential role for predicting tumor types, treatment response, and prognosis in various cancers, including head and neck, esophageal, lung, breast, and colorectal cancers 10 , 13 – 20 . Given the usefulness of CT texture analysis for prognosis predictions in various cancers, we have hypothesized that the quantitative texture features of pancreas head cancer measured on preoperative CT images might be useful for predicting the clinical outcome of patients with pancreas head cancer after curative resection.…”

Minichromosome maintenance protein 2 correlates with the malignant status and regulates proliferation and cell cycle in lung squamous cell carcinoma

“… 4 , 5 LUAD and LUSC are the two major histological types of lung cancer, accounting for 80% of lung cancer cases. 6 In recent decades, molecular targeted therapy has seen a rapid growth including the development of epidermal growth factor (EGF) receptor tyrosine kinase inhibitors and anaplastic lymphoma tyrosine kinase inhibitors, which are effective for the treatment of LUAD carrying activating mutations. 7 , 8 Due to lack of effective therapeutic target in LUSC patients, the overall survival of LUSC patients is significantly shorter compared with LUAD patients.…”

Arcabouço para Classificação, Recuperação por Conteúdo e Radiômica de Imagens Médicas: uma investigação de biomarcadores quantitativos para o câncer de pulmão

“…Correlação calcula a dependência linear dos níveis de cinza em uma região. A medida de homogeneidade é o inverso do contraste e resulta em grandes valores para níveis de cinza similares (PHILLIPS et al, 2017;OLIVEIRA, 2006).…”

“…As medidas de não-uniformidade caracterizam as similaridades entre os níveis de cinza de uma imagem e entre as sequências de comprimento de intensidades. A medida de porcentagem de sequência é a relação entre o número de sequências e o número total de sequências possíveis, logo, para imagens com estrutura de textura linear, o seu valor resultante é baixo (PHILLIPS et al, 2017;DAVNALL et al, 2012).…”

“…A complexidade calcula a quantidade de informação da textura da região. E por fim, o atributo de força mede o quão distinta é a textura primitiva (PHILLIPS et al, 2017;DAVNALL et al, 2012).…”