RESUMEN
Lung cancer screening (LCS) using annual computed tomography (CT) scanning significantly reduces mortality by detecting cancerous lung nodules at an earlier stage. Deep learning algorithms can improve nodule malignancy risk stratification. However, they have typically been used to analyse single time point CT data when detecting malignant nodules on either baseline or incident CT LCS rounds. Deep learning algorithms have the greatest value in two aspects. These approaches have great potential in assessing nodule change across time-series CT scans where subtle changes may be challenging to identify using the human eye alone. Moreover, they could be targeted to detect nodules developing on incident screening rounds, where cancers are generally smaller and more challenging to detect confidently. Here, we show the performance of our Deep learning-based Computer-Aided Diagnosis model integrating Nodule and Lung imaging data with clinical Metadata Longitudinally (DeepCAD-NLM-L) for malignancy prediction. DeepCAD-NLM-L showed improved performance (AUC = 88%) against models utilizing single time-point data alone. DeepCAD-NLM-L also demonstrated comparable and complementary performance to radiologists when interpreting the most challenging nodules typically found in LCS programs. It also demonstrated similar performance to radiologists when assessed on out-of-distribution imaging dataset. The results emphasize the advantages of using time-series and multimodal analyses when interpreting malignancy risk in LCS.
Asunto(s)
Aprendizaje Profundo , Detección Precoz del Cáncer , Neoplasias Pulmonares , Tomografía Computarizada por Rayos X , Humanos , Neoplasias Pulmonares/diagnóstico por imagen , Tomografía Computarizada por Rayos X/métodos , Detección Precoz del Cáncer/métodos , Interpretación de Imagen Radiográfica Asistida por Computador/métodos , Diagnóstico por Computador/métodos , AlgoritmosRESUMEN
BACKGROUND: The aim was to predict survival of glioblastoma at 8 months after radiotherapy (a period allowing for completing a typical course of adjuvant temozolomide), by applying deep learning to the first brain MRI after radiotherapy completion. METHODS: Retrospective and prospective data were collected from 206 consecutive glioblastoma, isocitrate dehydrogenase -wildtype patients diagnosed between March 2014 and February 2022 across 11 UK centers. Models were trained on 158 retrospective patients from 3 centers. Holdout test sets were retrospective (nâ =â 19; internal validation), and prospective (nâ =â 29; external validation from 8 distinct centers). Neural network branches for T2-weighted and contrast-enhanced T1-weighted inputs were concatenated to predict survival. A nonimaging branch (demographics/MGMT/treatment data) was also combined with the imaging model. We investigated the influence of individual MR sequences; nonimaging features; and weighted dense blocks pretrained for abnormality detection. RESULTS: The imaging model outperformed the nonimaging model in all test sets (area under the receiver-operating characteristic curve, AUC Pâ =â .038) and performed similarly to a combined imaging/nonimaging model (Pâ >â .05). Imaging, nonimaging, and combined models applied to amalgamated test sets gave AUCs of 0.93, 0.79, and 0.91. Initializing the imaging model with pretrained weights from 10 000s of brain MRIs improved performance considerably (amalgamated test sets without pretraining 0.64; Pâ =â .003). CONCLUSIONS: A deep learning model using MRI images after radiotherapy reliably and accurately determined survival of glioblastoma. The model serves as a prognostic biomarker identifying patients who will not survive beyond a typical course of adjuvant temozolomide, thereby stratifying patients into those who might require early second-line or clinical trial treatment.
Asunto(s)
Neoplasias Encefálicas , Glioblastoma , Imagen por Resonancia Magnética , Humanos , Glioblastoma/diagnóstico por imagen , Glioblastoma/radioterapia , Glioblastoma/mortalidad , Glioblastoma/patología , Imagen por Resonancia Magnética/métodos , Neoplasias Encefálicas/radioterapia , Neoplasias Encefálicas/diagnóstico por imagen , Neoplasias Encefálicas/mortalidad , Neoplasias Encefálicas/patología , Femenino , Masculino , Persona de Mediana Edad , Estudios Retrospectivos , Estudios Prospectivos , Anciano , Pronóstico , Aprendizaje Profundo , Adulto , Tasa de Supervivencia , Estudios de Seguimiento , Temozolomida/uso terapéuticoRESUMEN
Radiation-induced lung damage (RILD) is a common side effect of radiotherapy (RT). The ability to automatically segment, classify, and quantify different types of lung parenchymal change is essential to uncover underlying patterns of RILD and their evolution over time. A RILD dedicated tissue classification system was developed to describe lung parenchymal tissue changes on a voxel-wise level. The classification system was automated for segmentation of five lung tissue classes on computed tomography (CT) scans that described incrementally increasing tissue density, ranging from normal lung (Class 1) to consolidation (Class 5). For ground truth data generation, we employed a two-stage data annotation approach, akin to active learning. Manual segmentation was used to train a stage one auto-segmentation method. These results were manually refined and used to train the stage two auto-segmentation algorithm. The stage two auto-segmentation algorithm was an ensemble of six 2D Unets using different loss functions and numbers of input channels. The development dataset used in this study consisted of 40 cases, each with a pre-radiotherapy, 3-, 6-, 12-, and 24-month follow-up CT scans (n = 200 CT scans). The method was assessed on a hold-out test dataset of 6 cases (n = 30 CT scans). The global Dice score coefficients (DSC) achieved for each tissue class were: Class (1) 99% and 98%, Class (2) 71% and 44%, Class (3) 56% and 26%, Class (4) 79% and 47%, and Class (5) 96% and 92%, for development and test subsets, respectively. The lowest values for the test subsets were caused by imaging artefacts or reflected subgroups that occurred infrequently and with smaller overall parenchymal volumes. We performed qualitative evaluation on the test dataset presenting manual and auto-segmentation to a blinded independent radiologist to rate them as 'acceptable', 'minor disagreement' or 'major disagreement'. The auto-segmentation ratings were similar to the manual segmentation, both having approximately 90% of cases rated as acceptable. The proposed framework for auto-segmentation of different lung tissue classes produces acceptable results in the majority of cases and has the potential to facilitate future large studies of RILD.
RESUMEN
We present a novel classification system of the parenchymal features of radiation-induced lung damage (RILD). We developed a deep learning network to automate the delineation of five classes of parenchymal textures. We quantify the volumetric change in classes after radiotherapy in order to allow detailed, quantitative descriptions of the evolution of lung parenchyma up to 24 months after RT, and correlate these with radiotherapy dose and respiratory outcomes. Diagnostic CTs were available pre-RT, and at 3, 6, 12 and 24 months post-RT, for 46 subjects enrolled in a clinical trial of chemoradiotherapy for non-small cell lung cancer. All 230 CT scans were segmented using our network. The five parenchymal classes showed distinct temporal patterns. Moderate correlation was seen between change in tissue class volume and clinical and dosimetric parameters, e.g., the Pearson correlation coefficient was ≤0.49 between V30 and change in Class 2, and was 0.39 between change in Class 1 and decline in FVC. The effect of the local dose on tissue class revealed a strong dose-dependent relationship. Respiratory function measured by spirometry and MRC dyspnoea scores after radiotherapy correlated with the measured radiological RILD. We demonstrate the potential of using our approach to analyse and understand the morphological and functional evolution of RILD in greater detail than previously possible.
RESUMEN
Reducing radiation-induced side effects is one of the most important challenges in paediatric cancer treatment. Recently, there has been growing interest in using spatial normalisation to enable voxel-based analysis of radiation-induced toxicities in a variety of patient groups. The need to consider three-dimensional distribution of doses, rather than dose-volume histograms, is desirable but not yet explored in paediatric populations. In this paper, we investigate the feasibility of atlas construction and spatial normalisation in paediatric radiotherapy. We used planning computed tomography (CT) scans from twenty paediatric patients historically treated with craniospinal irradiation to generate a template CT that is suitable for spatial normalisation. This childhood cancer population representative template was constructed using groupwise image registration. An independent set of 53 subjects from a variety of childhood malignancies was then used to assess the quality of the propagation of new subjects to this common reference space using deformable image registration (i.e. spatial normalisation). The method was evaluated in terms of overall image similarity metrics, contour similarity and preservation of dose-volume properties. After spatial normalisation, we report a dice similarity coefficient of 0.95 ± 0.05, 0.85 ± 0.04, 0.96 ± 0.01, 0.91 ± 0.03, 0.83 ± 0.06 and 0.65 ± 0.16 for brain and spinal canal, ocular globes, lungs, liver, kidneys and bladder. We then demonstrated the potential advantages of an atlas-based approach to study the risk of second malignant neoplasms after radiotherapy. Our findings indicate satisfactory mapping between a heterogeneous group of patients and the template CT. The poorest performance was for organs in the abdominal and pelvic region, likely due to respiratory and physiological motion and to the highly deformable nature of abdominal organs. More specialised algorithms should be explored in the future to improve mapping in these regions. This study is the first step toward voxel-based analysis in radiation-induced toxicities following paediatric radiotherapy.
Asunto(s)
Neoplasias , Planificación de la Radioterapia Asistida por Computador , Algoritmos , Niño , Humanos , Neoplasias/diagnóstico por imagen , Neoplasias/radioterapia , Pelvis , Tomografía Computarizada por Rayos XRESUMEN
In the United States of America, almost 150,000 people are estimated to be diagnosed with colorectal cancer in 2020 and up to 35% of those are expected to present with oligometastatic disease. The term 'oligometastasis' was first used in 1995, however surgical literature describing liver resection for colorectal cancer dates back to the 1940s. Five-year survival rates of up to 42% with surgery alone for solitary lesions are reported. Modern trials have demonstrated median overall survival rates of over 80 months for patients with colorectal liver metastases treated with perioperative chemotherapy. Colorectal liver metastases have accordingly been described as 'proof of concept' for the oligometastatic theory.
Asunto(s)
Neoplasias Colorrectales , Neoplasias Hepáticas , Neoplasias Colorrectales/terapia , Humanos , Neoplasias Hepáticas/terapia , Resultado del TratamientoRESUMEN
BACKGROUND AND PURPOSE: Radiation-induced lung damage (RILD) is a common consequence of lung cancer radiotherapy (RT) with unclear evolution over time. We quantify radiological RILD longitudinally and correlate it with dosimetry and respiratory morbidity. MATERIALS AND METHODS: CTs were available pre-RT and at 3, 6, 12 and 24-months post-RT for forty-five subjects enrolled in a phase 1/2 clinical trial of isotoxic, dose-escalated chemoradiotherapy for locally advanced non-small cell lung cancer. Fifteen CT-based measures of parenchymal, pleural and lung volume change, and anatomical distortions, were calculated. Respiratory morbidity was assessed with the Medical Research Council (MRC) dyspnoea score and spirometric pulmonary function tests (PFTs): FVC, FEV1, FEV1/FVC and DLCO. RESULTS: FEV1, FEV1/FVC and MRC scores progressively declined post-RT; FVC decreased by 6-months before partially recovering. Radiologically, an early phase (3-6 months) of acute inflammation was characterised by reversible parenchymal change and non-progressive anatomical distortion. A phase of chronic scarring followed (6-24 months) with irreversible parenchymal change, progressive volume loss and anatomical distortion. Post-RT increase in contralateral lung volume was common. Normal lung volume shrinkage correlated longitudinally with mean lung dose (r = 0.30-0.40, p = 0.01-0.04). Radiological findings allowed separation of patients with predominant acute versus chronic RILD; subjects with predominantly chronic RILD had poorer pre-RT lung function. CONCLUSIONS: CT-based measures enable detailed quantification of the longitudinal evolution of RILD. The majority of patients developed progressive lung damage, even when the early phase was absent or mild. Pre-RT lung function and RT dosimetry may allow to identify subjects at increased risk of RILD.